Decision Tree Classification Method Research Articles

Using Artificial Intelligence Technology to Solve the Electronic Health Service by Processing the Online Case Information.

With the continuous improvement of economic level and the continuous development of science and technology in China, information technology has begun to integrate into all walks of life. Medical units have begun to change from the traditional medical system to the intelligent system, and the processing of online case information has become an important component of medical informationization. To improve the efficiency of dealing with online case information, this study proposes to establish a fully connected neural network model to deal with online cases. Using jieba word segmentation tool and data preprocessing technology, the data of electronic medical records are sorted out, and the data are quantified using Word2Vec and other tools, and the data on electronic medical records are converted into one-hot binary variables. The quantified data are trained into a fully connected neural model, and the accuracy rate is about 88%. It is compared with naive Bayes and decision tree classification methods, and then a comparative experiment is carried out by solving e-health services in different ways. The results show that the fully connected neural network model has the best classification effect: the highest accuracy rate is about 93.7%, the highest precision rate is about 94.0%, the highest recall rate is about 95.3%, and the highest F1 score is about 94.6%. However, using artificial intelligence technology to solve electronic health services has great advantages, among which efficiency, assistance, and service satisfaction are all higher than 90%, which provides favorable technical support for electronic health services.

Sistem Monitoring dan Deteksi Stres Pada Anak Berbasis Wearable Device

The need for monitoring of children today is very important, especially for children under five, whose physical and verbal abilities are still inadequate to be able to communicate effectively with their parents or caregivers about the conditions they are experiencing. Previous studies related to child safety that were studied generally focused on responses to events that could potentially harm children.This study aims to design a prototype child monitoring system consisting of a wearable device that is used on a child's wrist equipped with sensors and connected to a server via a wireless network. Monitoring software that runs on the server will collect all data parameters from wearable devices with built-in audio signal, temperature, and heart rate sensor then with machine learning algorithm implemented in software will allow the system to predict if stress conditions happen on children and then system can give warnings to child-caregiver through monitoring applications or SMS messages. Using the Decision Tree and Naive Bayes classification methods the system can effectively predict stress conditions in children with an accuracy of 82.8 percent using audio, temperature, and heart rate parameters. This shows that the system has the capability to contribute to increasing child safety in the supervision environment.

A new classification method for encrypted internet traffic using machine learning

The rate of internet usage in the world is over 62% and this rate is increasing day by day. With this increase, it becomes important to ensure the confidentiality of the information in the traffic flowing over the internet. Encryption algorithms and protocols are used for this purpose. This situation, which is beneficial for normal users, is also used by attackers to hide. Cyber attackers or hackers gain the ability to bypass security precautions such as IDS/IPS and antivirus systems with using encrypted traffic. Since payload analysis cannot be performed without deciphering the encrypted traffic, existing commercial security solutions fall short in this situation. In this study, it is aimed to classify the network traffic by analysing the outgoing and incoming data over the encrypted traffic using extreme gradient boosting (XGBoost), decision tree and random forest classification methods. Thus, without deciphering, it is possible to classify packets passing through encrypted traffic using some metadata like size and duration and to take precautions against attacks. ISCX VPN-NonVPN dataset was used to test the proposed model in this study. With the created framework, encrypted traffic was classified with a high success rate and 94.53% success was achieved by using the XGBoost classification method.

Evaluation of pleural fluid parameters related to cardiac diseases in cats.

Background and Aim:Cardiac disease is common in cats, and concurrent pleural effusion can worsen the prognosis. However, the definitive diagnosis of feline cardiac disease by echocardiography is limited in some areas. This study was designed to determine the indicators from fluid analysis obtained from pleural effusion to help diagnose cardiac disease in cats.Materials and Methods:A retrospective study was conducted. Data of 61 cats with pleural effusion were retrieved. The cats were divided into two groups: Cardiac disease (n=34) and non-cardiac disease (n=27) groups. Sex, neuter status, breed, age, weight, physical findings, fluid analysis results, radiographic findings, echocardiographic findings, and the presence of other diseases or conditions were recorded.Results:The Chi-square test showed the relationship between cardiac disease and the presence of abnormal heart sounds (p=0.0003), the N-terminal pro-B-type natriuretic peptide-positive result from serum samples (p=0.046), the presence of arterial thromboembolism (p<0.00001), and the presence of radiographic evidence of cardiomegaly and pulmonary edema (p=0.0002 and 0.001, respectively). The Mann–Whitney U-test showed a significant difference in protein concentration and specific gravity between the cardiac and non-cardiac disease groups (p=0.012 and 0.009, respectively). The decision tree classification method showed that protein concentrations of ≤3 g/dL were related to cardiac disease (sensitivity, 41.2% and specificity, 92.6%).Conclusion:The protein concentration in the pleural fluid may be used to distinguish cardiac and non-cardiac diseases in cats.

Classification of Toddler Nutrition Using C4.5 Decision Tree Method

Nutrition is very much needed in the growth of toddlers. It is very important to give babies a balanced nutritional intake at the right stage so that the baby grows healthy and is accustomed to a healthy lifestyle in the future. Children under five years of age are a group that is vulnerable to health and nutrition problems. In determining the nutritional status, it can be done in a system manner using the C4.5 decision tree classification method and entering several variables or attributes. The dataset tested was 853 toddlers. Classification is carried out to determine the nutritional status based on the weight/age (BB/U), height/age (TB/U) and weight/height (BB/TB) categories. The attributes used for the classification of BB/U are gender, weight and age. The attributes used for TB/U are gender, body length or height, and age. The attributes used for BB/TB are gender, weight, body length or height, and age. The average accuracy of the BB/U category is 90.16%, the average accuracy of the TB/U category is 76.64%, and the average accuracy of the BB/TB category is 83.83%.

Predicting Course Grade through Comprehensive Modelling of Students’ Learning Behavioral Pattern

While modelling students’ learning behavior or preferences has been found as a crucial indicator for their course achievement, very few studies have considered it in predicting achievement of students in online courses. This study aims to model students’ online learning behavior and accordingly predict their course achievement. First, feature vectors are developed using their aggregated action logs during a course. Second, some of these feature vectors are quantified into three numeric values that are used to model students’ learning behavior, namely, accessing learning resources (content access), engaging with peers (engagement), and taking assessment tests (assessment). Both students’ feature vectors and behavior model constitute a comprehensive students’ learning behavioral pattern which is later used for prediction of their course achievement. Lastly, using a multiple criteria decision-making method (i.e., TOPSIS), the best classification methods were identified for courses with different sizes. Our findings revealed that the proposed generalizable approach could successfully predict students’ achievement in courses with different numbers of students and features, showing the stability of the approach. Decision Tree and AdaBoost classification methods appeared to outperform other existing methods on different datasets. Moreover, our results provide evidence that it is feasible to predict students’ course achievement with a high accuracy through modelling their learning behavior during online courses.

RFM-based repurchase behavior for customer classification and segmentation

Customer behavior modeling and classification are well-studied areas for applications in retail. Past studies implemented the purchase behavior modeling based on the physical behavior of a subject. In this research, we apply the recency, frequency, and monetary (RFM) model and data modeling techniques to detect behavior patterns for a customer. Each transaction attributed to a customer is part of one's behavior, and an instance of the feature vector, it is modeled on a set of transactions to constitute repurchase behavior. The proposed scheme is validated by simulating a publicly accessible real-world data set with a need-tailored multi-layer perceptron (MLP) and also support vector machine (SVM) and decision tree classification (DTC) methods. The experiments yield a high customer classification rate of more than 97% for the different numbers of the customers. Empirical analysis shows that eight transactions are sufficient to classify a customer with high accuracy.

Extracting Information on Wetlands in Northeast China Based on Time Series FY3/MERSI Data

Using Fengyun Medium Resolution Spectral Imager (FY3/MERSI) data from 2011 to 2018, this paper analyzed the characteristics of original spectra and the normalized difference vegetation index (NDVI) of lakes, reservoirs, rivers, paddy fields and swamps in Northeast China, A large-scale wetland extraction model was built using the decision tree classification method, and accuracy was verified in typical sites using China High-resolution Earth Observation System (CHEOS-1) data. The results showed that there were differences in the spectral curves and NDVI of different wetland types, especially the swamps, paddy fields and other landforms that showed a growth cycle with more significant differences in spectral curves and index curves than those of lakes, reservoirs and rivers. The total area of wetlands in Northeast China was 79,123.4 km2, including 5262.3 k m2 of lake and reservoir wetlands, 6514.7 km2 of river wetlands, 15284.7 k m2 of swamp wetlands and 52061.7 km2 of paddy fields. The accuracy verification showed that the area accuracy of wetlands was over 91.8%, the overall classification accuracy of wetlands was over 84.8% and the Kappa coefficient was over 0.6446.

Decision-Tree-Initialized Dendritic Neuron Model for Fast and Accurate Data Classification

This work proposes a decision tree (DT)-based method for initializing a dendritic neuron model (DNM). Neural networks become larger and larger, thus consuming more and more computing resources. This calls for a strong need to prune neurons that do not contribute much to their network's output. Pruning those with low contribution may lead to a loss of accuracy of DNM. Our proposed method is novel because 1) it can reduce the number of dendrites in DNM while improving training efficiency without affecting accuracy and 2) it can select proper initialization weight and threshold of neurons. The Adam algorithm is used to train DNM after its initialization with our proposed DT-based method. To verify its effectiveness, we apply it to seven benchmark datasets. The results show that decision-tree-initialized DNM is significantly better than the original DNM, k-nearest neighbor, support vector machine, back-propagation neural network, and DT classification methods. It exhibits the lowest model complexity and highest training speed without losing any accuracy. The interactions among attributes can also be observed in its dendritic neurons.

Enhancement of Water Index Feature of Satellite Image in Mountainous Areas with Slope Information

A novel slope adjusted water index (SAWI) is proposed to enhance the performance of the modified normalized difference water index (MNDWI) in mountainous areas, where water body and terrain shadow are prone to be confused, due to their similar spectral reflectance in the green and medium-wave infrared (MIR) bands. To overcome this problem, this method introduces a slope information derived from readily available ASTER GDEM-V2 data to the MNDWI, which provides a different scaling parameter to the MIR band for each pixel, such that the difference between terrain shadow and open water can be easily separated in mountainous areas. To validate the effectiveness of the proposed method, four typical sub-scenes clipped from the Operational Land Imager image with different terrain conditions were analyzed, and the results demonstrate that our method can not only possess the ability to relieve the effect of terrain shadow in rugged regions, but also enhance the subtle perception of narrow water body in plain areas, when compared with the MNDWI method. Comparisons with the normalized difference water index and the decision tree classification method were also implemented, and experimental results consistently show that the SAWI outperforms them for all the cases in terms of the used recall, precision and area under curve measurements.

Jamming Efficiency Analysis Based on the Range Profile of Target With Chaff

Chaff cloud is widely used in target covering. In this paper, a jamming performance estimation strategy is presented for the elliptical and cubic chaff clouds. The range profiles of the composite models of the plane with the chaff cloud are experimentally accessed in an anechoic chamber using a stepped-frequency waveform measurement system. Then, dimensions, characteristic length, and distributing entropy of the equivalent scattering centers of the plane and the jammer are extracted from the measured range profiles, respectively. Based on these features, support vector machines, naive Bayesian classification, and decision tree classification methods are employed to determine the recognition rate of the target under the chaff jamming, and then determine the jamming efficiency of the two kinds of chaff clouds. Results show that two types of chaff clouds are able to reduce the target recognition rate. Besides, when the radar uses the Euclidean distance and decision tree classification methods to complete the recognition task, a good jamming efficiency can be achieved by releasing the elliptical or the cubic chaff cloud. Meanwhile, a low level of jamming performance outcomes using the support vector machines classification method. It is also found that the chaff cloud released from the side of the plane achieves a better jamming performance compared with the other releasing locations. Finally, the influence of environmental noise on the recognition rate of the plane is studied. Estimating results show that the recognition rates decrease with the increasing of the power level of the noise. When the transmitting power level of the noise reaches 1.2 times the reflected power level of the target, it is quite hard to estimate the jamming performance of two kinds of chaff clouds.

A gait recognition method for a moving target image in sports based on a decision tree

In order to overcome the low accuracy of traditional gait recognition methods, a new gait recognition method based on a decision tree is proposed. The decision tree classification method is used to obtain the effective gait features in the sports target image. Based on the acquired effective gait features, the weighted block sparse representation method is used to realise the gait recognition of the sports target image. The experimental results show that this method has high recognition accuracy for the gait in the sports target image with small area occlusion and no occlusion. When the dimension is 301, the recognition accuracy of this method is 97.5%. Compared with similar recognition methods, the recognition accuracy of this method is significant and can be used in the task of gait recognition of a sports target image.

Research on Recognition and Classification of Folk Music Based on Feature Extraction Algorithm

In this study, the feature extraction algorithm for folk music was analyzed. The features of folk music were extracted in aspects of time domain and frequency domain. Then, a support vector machine (SVM) was selected to identify and classify folk music. It was found that the performance of SVM was the best when was 2 6 and was 4; the recognition rate of using only one feature was inferior to that of using all features; the highest recognition rate of SVM was 92.76%; compared with back propagation neural network (BPNN) and decision tree classification method, SVM had a higher recognition rate. The experimental results show the effectiveness of SVM, which can be applied in practice.

A Water Body Extraction Methods Comparison Based on FengYun Satellite Data: A Case Study of Poyang Lake Region, China

Water body extraction can help eco-environmental policymakers to intuitively grasp surface water resources. Remote sensing technology can accurately and quickly extract surface water information, which is of great significance for monitoring surface water changes. Fengyun satellite images have the advantages of high time resolution and multispectral bands. This provides important image data suitable for high-frequency surface water monitoring. Based on Fengyun 3 medium resolution spectral imager (FY-3/MERSI) data, 7 methods were applied in this study, which include single-band threshold method, water body index method, knowledge decision tree classification method, supervised classification method, unsupervised classification method, spectral matching based on discrete particle swarm optimization (SMDPSO), and improved spectral matching based on discrete particle swarm optimization with linear feature enhancement (SMDPSO+LFE). These methods were used to extract the land surface water of Poyang Lake, check the samples from the Landsat image with similar times to the FY-3 images, and calculate the classification accuracy via the confusion matrix. The results showed that the overall classification accuracy (OA) of the SMDPSO+LFE is 97.64%, and the Kappa coefficient is 0.95. To analyze the stability of the surface water extracted by SMDPSO+LFE in different regions, this paper selected eight test sites with different surface water types, landscapes, and terrains to extract surface water. Based on an analysis of the land surface water results at the eight test sites, every OA in the eight sites was higher than 94.5%, the Kappa coefficient was greater than 0.88. In conclusion, the SMDPSO+LFE is found to be the most suitable method among the 7 methods and effectively distinguish between different surface water bodies and backgrounds with good stability.

Monitoring of rice lodging using Sentinel-1 data

Synthetic Aperture Radar (SAR) can monitor rice regardless of time and weather condition, and the ability of crop lodge monitoring has been demonstrated by previous studies. However, there have no study about monitoring of rice lodging using satellite-based SAR. In this study, we extracted backscatter coefficient (BC) and H/A/Alpha polarimetric parameters from dual-polarized Sentinel-1 SAR data, and a lodging sensitivity factor γ was constructed for selecting optimal radar feature parameter (ORFP) which is highly sensitivity to lodging rice. Then, the decision tree classification method was used with multiple ORFPs to classify the healthy and lodging rice plots. We firstly acquired shape of rice region using Sentinel-2 image and Maximum likelihood classification method for eliminating the influence of other features before classification of lodging rice. The result showed that the overall accuracy of 87.18% is achieved with the combination of ORFPs and decision tree.

Cosmetics Customer Segmentation and Profile in Indonesia Using Clustering and Classification Algorithm

The cosmetics business competition in Indonesia is currently increasing so rapidly, cosmetics customers have spread to various brands, and according to taste. The customer for the company is an asset that is very important for business continuity, so that good customer management can increase company revenue. However, it is not easy to manage customers if they cannot read the characteristics of customers, to carry out appropriate business strategies. So that requires a customer analysis method that can provide recommendations for the company. RFM is one of the most widely used analytical methods for analyzing customers through segmentation and profiling of customers. In addition to segmenting, the customer profile is also a very important factor in analyzing customers, ALC is a form of a customer profile that can be used. RFM + ALC method is not easy to do with very large customer history data, so data mining is needed to help conduct the RFM + ALC analysis. Data mining methods using the clustering function with K-Means and the use of the Elbow method to get the most optimal amount of K in the clustering process can be a model used to segment with RFM, as well as the Naïve Bayes and Decision Tree classification methods to determine ALC profile factors the most influential customer. The results of clustering modeling carried out produce two dominant customer segments. While the Naïve Bayes classification model of the ALC factor can provide recommendations for the most influential customer profiles, with the highest level of accuracy with an accuracy value of 65.87% when compared to the Decision Tree.

Changes in land cover and ecological stress in Borneo based on remote sensing and an ecological footprint method

Changes in land cover and ecological stressors are known to reflect the influences of human activities on regional environments and are also indicators of sustainable development. In this research, Borneo was selected as the study area. The data were sourced from Landsat TM image data obtained in 1990, 2000 and 2010, SRTM DEM data, and DMSP/OLS night-time satellite data, along with socioeconomic information, including regional population, biological resource consumption and energy consumption data. The vegetation brightness index (VBI) and the filtered normalized difference built-up index (FNDBI) are proposed, and the overall classification accuracy reached 87% when combined with decision tree classification and visual interpretation methods. Based on the traditional ecological footprint method, a dynamic calculation method for the production factor is proposed. The ecological footprint, ecological carrying capacity, and ecological deficit/surplus of Borneo in 1990, 2000, and 2010 were then calculated, and a method for creating the corresponding grid-based spatial distribution map was proposed. The effects of human activities on land cover and ecological stress in Borneo from 1990 to 2010 were analyzed in this study. The results showed that the tropical rainforests of Borneo decreased by 13% over two decades and dramatically changed to shrublands, plantations, and arable land areas. The ecological pressure increased from the central mountains to the coastal plains, and ecological deficits appeared in the coastal zones with altitudes less than 150 m in the West Kalimantan, South Kalimantan, and Sabah regions, which indicated a trend of gradual expansion. Urban construction, plantations, logging, mining, forest fires, and other human activities have interfered with natural systems, and this has led to major pressures being placed on regional sustainable development and ecological security, as well as influencing the ecological stability of other global regions.

Spatial Distribution of Rice Planting Based on Data Fusion Model in Southern China

Acquiring the real and accurate spatial distribution of rice planting in the agricultural area of the basin is the precondition of implementing precision agricultural management, and the basis of building the database of agricultural non-point source pollution risk control and management. In order to overcome the characteristics of scattered rice distribution in southern China, such as small planting area, and instantaneous and periodicity of satellite sensor imaging, ESTARFM model was used to fuse NDVI data of MODIS09A1 and Landsat 8. The NDVI image data with both high spatial resolution and high temporal resolution were obtained after fused. The conditions and thresholds of decision tree classification method were determined with the help of curve feature information of NDVI indices of various crops in the growing period. The main results as follows: The spatial distribution of paddy ecosystem was extracted by multi-source data fusion and decision tree classification to meet the accuracy verification requirements; three cropping patterns, early rice, middle-season rice and late rice were extracted.

Animated Character Style Investigation with Decision Tree Classification

Although animated characters are based on human features, these features are exaggerated. These exaggerations greatly differ by country, gender, and the character’s role in the story. This study investigated the characteristics of US and Japanese character designs and the similarities and differences or even the differences in exaggerations between them. In particular, these similarities and differences can be used to formulate a shared set of principles for US and Japanese animated character designs; 90 Japanese and 90 US cartoon characters were analyzed. Lengths for 20 parts of the body were obtained for prototypical real human bodies and animated characters from Japan and the United States. The distributions of lengths were determined, for all characters and for characters as segmented by country, gender, and the character’s role in the story. We also compared the body part lengths of animated characters and prototypical real human bodies, noting whether exaggerations were towards augmentation or diminishment. In addition, a decision tree classification method was used to determine the required body length parameters for identifying the classification conditions of animated characters by country, gender, and character’s role in the story. The results indicated that both US and Japanese male animated characters tend to feature exaggerations in head and body sizes, with exaggerations for US characters being more obvious. The decision tree only required five length parameters of the head and chest to distinguish between US and Japanese animated characters (accuracy = 94.48% and 67.46% for the training and testing groups, respectively). Through a decision tree method, this study quantitatively revealed the exaggeration patterns in animated characters and their differences by country, gender, and character’s role in the story. The results serve as a reference for designers and researchers of animated character model designs with regards to quantifying and classifying character exaggerations.

Bank CRM Optimization Using Predictive Classification Based on the Support Vector Machine Method

ABSTRACT This paper proposes a predictive approach to segmenting credit card users, based on their value to the bank. The approach combines the Recency, Frequency and Monetary (RFM) method, clustering using the k-means method, and predictive classification by the Support Vector Machine (SVM) method. Clustering by non-encoded RFM attributes overcomes the subjectivity in selecting the number of segments and losing information (small differences in the values of these attributes) which are problems of classic RFM segmentation. In order to overcome the problem of class imbalance in predictive classification (which occurs due to the small number of valuable customers), the Support Vector Machine (SVM) method was applied as a pre-processor of data due to its extraordinary generalization capabilities. The end result of predictive classification should be a set of rules that describes the identified customer segments in order to tailor the offer to each segment individually. The extraction of rules from the SVM output was achieved using the Decision Tree (DT) classification method. Using a proposed approach that addresses the issue of the small class, marketing managers can more effectively target the most valuable customers, thereby increasing revenue, but also reducing unnecessary costs due to wrongly targeted valuable clients.